arXiv subjects

Shaoqiu Zhang

Publications and source records attributed to Shaoqiu Zhang.

9 recordsLinked to original sources

arXiv2026

ET-Prune: Evidence-Aware Dynamic Budgeting for Visual Token Pruning in Text-Rich MLLMs

Visual token pruning reduces the inference cost of multimodal large language models, but a fixed token ratio is poorly matched to text-rich inputs. In OCR-centric tasks, decisive evidence can be a small number, label, or field whose relevance is specified by the question; indiscriminate pruning can erase that evidence while retaining visually salient but irrelevant regions. We present ET-Prune, a training-free framework that casts pruning as evidence allocation. It derives question-conditioned evidence from a decoder-side partial query-key block, safeguards text-like spatial regions, and converts evidence uncertainty and density into a sample-specific token floor. Three progressive middle-layer events then move the sequence toward this budget, retaining more tokens for diffuse or text-dense evidence and pruning concentrated evidence more aggressively. At the observed point estimates from one deterministic pass per configuration, ET-Prune leads or ties among pruned methods in all six backbone-benchmark comparisons at roughly half tokens. On OCRBench-v2, it leads the strongest pruned baselines by 1.80 and 0.68 percentage points on Qwen3-VL-8B and InternVL3.5-8B, respectively, while retaining about half of the visual tokens; on MMBench v1.1, it reaches 0.8467 circular exact-matching accuracy versus 0.8437 for Vanilla at 54.45% average visual-token retention. These results show a favorable observed quality-cost trade-off for evidence-aware dynamic budgeting in text-rich multimodal inference.

cs.CV↗

arXiv2026

WorldDynCache: Risk-Controlled Latent Dynamics Approximation for Diffusion World Model

Diffusion world models generate high-quality futures, but re- peated transformer evaluations make inference prohibitively slow. Existing caches reuse intermediate features, selectively update tokens, or reuse and extrapolate denoising outputs ac- cording to local drift or short native-space histories. These criteria can miss both approximation-induced latent transition defects that accumulate across skipped steps and phase- or condition-dependent changes in the direction of latent evo- lution. We propose WorldDynCache, a risk-controlled latent dynamics approximation framework with two core compo- nents. First, a lightweight latent-transition risk estimator tracks the accumulated future impact of approximation defects and calibrates its predictions against counterfactual defects ob- served at exact anchors. Second, a condition- and phase- aware lifted latent surrogate approximates latent evolution without extra transformer evaluations. On HunyuanVoyager- 13B and Aether-5B, WorldDynCache achieves 4.92 times and 2.15 times speedups, respectively, while attaining the best gen- eration quality among the compared caching methods across WorldScore, PSNR, SSIM, and LPIPS.

cs.LG↗

arXiv2026

SWE-Pruner Pro: The Coder LLM Already Knows What to Prune

Pruning long context for coding agents has been a vital technology for efficient context management. While existing context pruning methods such as SWE-Pruner realize this by attaching a separate code classifier, we find the agent itself encodes internal representations indicating the relevance of code context when reading tool output. Based on this finding, we propose SWE-Pruner Pro, which prunes tool outputs directly inside the agent. Concretely, a small head turns the agent's own internal representations into a keep-or-prune label for each line, with a length-aware embedding keyed to each tool output's line count. Across two open-weight backbones and four multi-turn benchmarks, SWE-Pruner Pro saves up to 39% of prompt and completion tokens while preserving task quality, with bounded inference overhead. Notably, on MiMo-V2-Flash SWE-Pruner Pro additionally raises the SWE-Bench Verified resolve rate by +3.8% and the long-context Oolong accuracy by +2.2 points.

cs.CL↗

arXiv2026

FastContext: Training Efficient Repository Explorer for Coding Agents

Large Language Model (LLM) coding agents have achieved strong results on software engineering tasks, yet repository exploration remains a major bottleneck: locating relevant code consumes substantial token budget and pollutes the agent's context with irrelevant snippets. In most agents, the same model explores the repository and solves the task, leaving exploratory reads and searches in the solver's history. We present FastContext, a dedicated exploration subagent that separates repository exploration from solving. Invoked on demand, FastContext issues parallel tool calls and returns concise file paths and line ranges as focused context. FastContext is powered by specialized exploration models spanning 4B--30B parameters. We bootstrap them from strong reference-model trajectories and refine them with task-grounded rewards for broad first-turn search, multi-turn evidence gathering, and precise citation generation. Across SWE-bench Multilingual, SWE-bench Pro, and SWE-QA, integrating FastContext into Mini-SWE-Agent improves end-to-end resolution rates up to 5.5% while reducing coding-agent token consumption up to 60%, with marginal overhead. These results show that repository exploration can be separated from solving and handled effectively by specialized models. Code and data: https://github.com/microsoft/fastcontext

cs.SE↗

arXiv2026

SWE-Explore: Benchmarking How Coding Agents Explore Repositories

Repository-level coding benchmarks such as SWE-bench have driven a rapid surge in the capabilities of coding agents. Yet they usually treat coding tasks as a holistic, binary prediction problem (e.g., resolved or unresolved), neglecting fine-grained agent capabilities such as repository understanding, context retrieval, code localization, and bug diagnosis. In this paper, we introduce SWE-Explore, a benchmark that isolates the evaluation of repository exploration, a critical capability of coding agents. Given a repository and an issue, SWE-Explore asks an explorer to return a ranked list of relevant code regions under a fixed line budget. SWE-Explore covers 848 issues across 10 programming languages and 203 open-source repositories. For each instance, we derive line-level ground truth from independent agent trajectories that successfully solved the same issue, distilling the specific code regions their solution paths actually consulted. We evaluate exploration along coverage, ranking, and context-efficiency dimensions, showing that these metrics strongly track downstream repair behavior. Across a broad set of retrieval methods, general coding agents, and specialized localizers, we find that agentic explorers form a clear tier above classical retrieval. While file-level localization is already strong for modern methods, line-level coverage and efficient ranking remain the key axes differentiating state-of-the-art explorers.

cs.SE↗

arXiv2026

Elastic-dLLM: Position Preserving Context Compression and Augmentation of Diffusion LLMs

Unlike autoregressive models, which generate one token at a time, dLLMs denoise a chunk of [MASK] tokens jointly and sample one or more tokens per step; despite enabling parallel decoding, this process incurs substantial computational cost due to the large chunk size of masked tokens. We observe that much of this cost is spent on repeatedly processing the preceding context and many [MASK] tokens with the same feature representations, indicating considerable computational redundancy. In this work, we revisit dLLM's redundancy from the perspective of [MASK] tokens. Through systematic analysis, we verify the redundancy of [MASK] tokens while revealing their critical role in providing structural information. Guided by these findings, we propose position-preserving [MASK] token compression and terminal-aware augmentation. By compressing redundant [MASK] computation, this approach accelerates decoding and further provides a natural extension toward context-folding-like long-context scaling under limited input-length constraints for full-sequence dLLMs such as LLaDA-8B-Instruct and LLaDA-1.5. Moreover, for block dLLMs such as LLaDA2.0-mini, it augments the context with a protected terminal [MASK] token to enhance generation quality with negligible overhead.

cs.LG↗

arXiv2026

AdaTSQ: Pushing the Pareto Frontier of Diffusion Transformers via Temporal-Sensitivity Quantization

Diffusion Transformers (DiTs) have emerged as the state-of-the-art backbone for high-fidelity image and video generation. However, their massive computational cost and memory footprint hinder deployment on edge devices. While post-training quantization (PTQ) has proven effective for large language models (LLMs), directly applying existing methods to DiTs yields suboptimal results due to the neglect of the unique temporal dynamics inherent in diffusion processes. In this paper, we propose AdaTSQ, a novel PTQ framework that pushes the Pareto frontier of efficiency and quality by exploiting the temporal sensitivity of DiTs. First, we propose a Pareto-aware timestep-dynamic bit-width allocation strategy. We model the quantization policy search as a constrained pathfinding problem. We utilize a beam search algorithm guided by end-to-end reconstruction error to dynamically assign layer-wise bit-widths across different timesteps. Second, we propose a Fisher-guided temporal calibration mechanism. It leverages temporal Fisher information to prioritize calibration data from highly sensitive timesteps, seamlessly integrating with Hessian-based weight optimization. Extensive experiments on four advanced DiTs (e.g., Flux-Dev, Flux-Schnell, Z-Image, and Wan2.1) demonstrate that AdaTSQ significantly outperforms state-of-the-art methods like SVDQuant and ViDiT-Q. Our code will be released at https://github.com/Qiushao-E/AdaTSQ.

cs.CV↗

arXiv2026

D$^2$Quant: Accurate Low-bit Post-Training Weight Quantization for LLMs

Large language models (LLMs) deliver strong performance, but their high compute and memory costs make deployment difficult in resource-constrained scenarios. Weight-only post-training quantization (PTQ) is appealing, as it reduces memory usage and enables practical speedup without low-bit operators or specialized hardware. However, accuracy often degrades significantly in weight-only PTQ at sub-4-bit precision, and our analysis identifies two main causes: (1) down-projection matrices are a well-known quantization bottleneck, but maintaining their fidelity often requires extra bit-width; (2) weight quantization induces activation deviations, but effective correction strategies remain underexplored. To address these issues, we propose D$^2$Quant, a novel weight-only PTQ framework that improves quantization from both the weight and activation perspectives. On the weight side, we design a Dual-Scale Quantizer (DSQ) tailored to down-projection matrices, with an absorbable scaling factor that significantly improves accuracy without increasing the bit budget. On the activation side, we propose Deviation-Aware Correction (DAC), which incorporates a mean-shift correction within LayerNorm to mitigate quantization-induced activation distribution shifts. Extensive experiments across multiple LLM families and evaluation metrics show that D$^2$Quant delivers superior performance for weight-only PTQ at sub-4-bit precision. The code and models will be available at https://github.com/XIANGLONGYAN/D2Quant.

cs.LG↗

arXiv2025

CLQ: Cross-Layer Guided Orthogonal-based Quantization for Diffusion Transformers

Visual generation quality has been greatly promoted with the rapid advances in diffusion transformers (DiTs), which is attributed to the scaling of model size and complexity. However, these attributions also hinder the practical deployment of DiTs on edge devices, limiting their development and application. Serve as an efficient model compression technique, model post-training quantization (PTQ) can reduce the memory consumption and speed up the inference, with inevitable performance degradation. To alleviate the degradation, we propose CLQ, a cross-layer guided orthogonal-based quantization method for DiTs. To be specific, CLQ consists of three key designs. First, we observe that the calibration data used by most of the PTQ methods can not honestly represent the distribution of the activations. Therefore, we propose cross-block calibration (CBC) to obtain accurate calibration data, with which the quantization can be better guided. Second, we propose orthogonal-based smoothing (OBS), which quantifies the outlier score of each channel and leverages block Hadamard matrix to smooth the outliers with negligible overhead. Third, we propose cross-layer parameter searching (CLPS) to search. We evaluate CLQ with both image generation and video generation models and successfully compress the model into W4A4 with negligible degradation in visual quality and metrics. CLQ achieves 3.98x memory saving and 3.95x speedup. Our code is available at \hyperlink{https://github.com/Kai-Liu001/CLQ}{https://github.com/Kai-Liu001/CLQ}.

cs.CV↗